Accurate cellular link bandwidth prediction can benefit upper-layer protocols significantly. In this paper, we investigate how to predict cellular link bandwidth in LTE networks. We first conduct an extensive measurement study in two major commercial LTE networks in the US, and identify five types of lower-layer information that are correlated with cellular link bandwidth. We then develop a machine learning based prediction framework, LinkForecast, that identifies the most important features (from both upper and lower layers) and uses these features to predict link bandwidth in realtime. Our evaluation shows that LinkForecast is lightweight and the prediction is highly accurate: At the time granularity of one second, the average prediction error is in the range of 3.9 to 17.0 percent for all the scenarios we explore. We further investigate the prediction performance when using lower-layer features obtained through standard APIs provided by the operating system, instead of specialized tools. Our results show that, while the features thus obtained have lower fidelity compared to those from specialized tools, they lead to similar prediction accuracy, indicating that our approach can be easily used over commercial off-the-shelf mobile devices.

Detecting node failures in mobile wireless networks is very challenging because the network topology can be highly dynamic, the network may not be always connected, and the resources are limited. In this paper, we take a probabilistic approach and propose two node failure detection schemes that systematically combine localized monitoring, location estimation and node collaboration. Extensive simulation results in both connected and disconnected networks demonstrate that our schemes achieve high failure detection rates (close to an upper bound) and low false positive rates, and incur low communication overhead. Compared to approaches that use centralized monitoring, our approach has up to 80 percent lower communication overhead, and only slightly lower detection rates and slightly higher false positive rates. In addition, our approach has the advantage that it is applicable to both connected and disconnected networks while centralized monitoring is only applicable to connected networks. Compared to other approaches that use localized monitoring, our approach has similar failure detection rates, up to 57 percent lower communication overhead and much lower false positive rates (e.g., 0.01 versus 0.27 in some settings).

Neighbor discovery is one of the first steps in configuring and managing a wireless network. Most existing studies on neighbor discovery assume a single-packet reception model where only a single packet can be received successfully at a receiver. In this paper, motivated by the increasing prevalence of multipacket reception (MPR) technologies such as CDMA and MIMO, we study neighbor discovery in MPR networks that allow packets from multiple simultaneous transmitters to be received successfully at a receiver. Starting with a clique of n nodes, we first analyze a simple Aloha-like algorithm and show that it takes Θ((n ln n)/k) time to discover all neighbors with high probability when allowing up to k simultaneous transmissions. We then design two adaptive neighbor discovery algorithms that dynamically adjust the transmission probability for each node. We show that the adaptive algorithms yield a Θ(ln n) improvement over the Aloha-like scheme for a clique with n nodes and are thus order-optimal. Finally, we analyze our algorithms in a general multi-hop network setting. We show an upper bound of O((Δ ln n)/k) for the Aloha-like algorithm when the maximum node degree is Δ, which is at most a factor ln n worse than the optimal. In addition, when Δ is large, we show that the adaptive algorithms are orderoptimal, i.e., have a running time of O(Δ/k) which matches the lower bound for the problem.

Smart mobile handheld devices (MHDs) are being adopted at a fast speed. Compared to wireless non-handheld devices (NHDs), MHDs tend to be more mobile and can be used more opportunistically. In this paper, we study two important network usage characteristics of MHDs, namely session lengths and IP address usage, in a university campus WiFi network. Specifically, we analyze two five-week long DHCP traces collected from the network, characterize session lengths of MHDs, and develop two hyper-exponential models to capture the distribution of session lengths.We further characterize the IP address usage of MHDs, and develop two analytical models to predict the number of concurrent IP addresses that are being used by MHDs at one point of time. Goodness of fit tests indicate that our analytical models of session lengths provide good fit, and evaluation results demonstrate that the predictions from our models for IP address usage are accurate. Our results provide important insights on managing MHDs as they are being adopted rapidly in WiFi networks.

In this paper, we investigate how in-network aggregation approach impacts the target tracking quality in multi-hop wireless sensor networks under network delays. Specifically, we use the mean squared error (MSE) of the target location estimate to quantify the target tracking quality, and investigate how in-network aggregation affects the MSE. To obtain insights without being obscured by onerous mathematical details, we assume a Brownian motion mobility model for the target, Gaussian measurement noise for the sensors, and independent per-hop delays. Under the above assumptions, we first propose an aggregation scheme that preserves a sufficient statistic for optimal tracking under data aggregation at the intermediate nodes and arbitrary network delays. We then analytically study the impact of aggregation in three increasingly more complicated scenarios: single task tracking with only transmission delay, single task tracking with both transmission delay and queueing delay at intermediate nodes, and multi-task tracking. Our results demonstrate that in-network aggregation improves tracking quality in all three scenarios. Furthermore, our analysis provides guidelines on how to choose aggregation parameters in practice.

Smart mobile handheld devices (MHDs) such as smartphones have been used for a wide range of applications. Despite the recent flurry of research on various aspects of smart MHDs, little is known about their network performance in WiFi networks. In this paper, we measure the network performance of smart MHDs inside a university campus WiFi network, and identify the dominant factors that affect the network performance. Specifically, we analyze 2.9TB of data collected over three days by a monitor that is located at a gateway router of the network, and make the following findings: (1) Compared to non-handheld devices (NHDs), MHDs use well provisioned Akamai and Google servers more heavily, which boosts the overall network performance of MHDs. Furthermore, MHD flows, particularly short flows, benefit from the large initial congestion window that has been adopted by Akamai and Google servers. (2) MHDs tend to have larger local delays inside the WiFi network and are more adversely affected by the number of concurrent flows. (3) Earlier versions of Android OS (before 4.X) cannot take advantage of the large initial congestion window adopted by many servers. On the other hand, the large receive window adopted by iOS is not fully utilized by most flows, potentially leading to waste of resources. (4) Some application-level protocols cause inefficient use of network and operating system resources of MHDs in WiFi networks. Our observations provide valuable insights on content distribution, server provisioning, MHD system design, and application-level protocol design.

Faulty components in a network need to be localized and repaired to sustain the health of the network. In this paper, we propose a novel approach that carefully combines active and passive measurements to localize faults in wireless sensor networks. More specifically, we formulate a problem of optimal sequential testing guided by end-to-end data. This problem determines an optimal testing sequence of network components based on end-to-end data in sensor networks to minimize expected testing cost. We prove that this problem is NP-hard, and propose a recursive approach to solve it. This approach leads to a polynomial-time optimal algorithm for line topologies while requiring exponential running time for general topologies. We further develop two polynomial-time heuristic schemes that are applicable to general topologies. Extensive simulation shows that our heuristic schemes only require testing a very small set of network components to localize and repair all faults in the network. Our approach is superior to using active and passive measurements in isolation. It also outperforms the state-of-the-art approaches that localize and repair all faults in a network.

In this paper, we propose a classification scheme that differentiates Ethernet and WLAN TCP flows based on measurements collected passively at the edge of a network. This scheme computes two quantities, the fraction of wireless TCP flows and the degree of belief that a TCP flow traverses a WLAN inside the network, using an iterative Bayesian inference algorithm that we developed. We prove that this iterative Bayesian inference algorithm converges to the unique maximum likelihood estimate (MLE) of these two quantities. Furthermore, it has the advantage that it can handle any general K-classification problem given the marginal distributions of these classes. Numerical and experimental evaluations demonstrate that our classification scheme obtains accurate results. We apply this scheme to two sets of traces collected from two campus networks: one set collected from UMass in mid 2005 and the other collected from UConn in late 2010. Our technique infers that 4%-7% and 52%-55% of incoming TCP flows traverse an IEEE 802.11 wireless link in these two networks, respectively.

Neighbor discovery is one of the first steps in configuring and managing a wireless network. Most existing studies on neighbor discovery assume a single-packet reception model where only a single packet can be received successfully at a receiver. In this paper, motivated by the increasing prevalence of multipacket reception (MPR) technologies such as CDMA and MIMO, we study neighbor discovery in MPR networks that allow multiple packets to be received successfully at a receiver. More specifically, we design and analyze a series of randomized algorithms for neighbor discovery in MPR networks. We start with a simple Aloha-like algorithm that assumes synchronous node transmissions and the number of neighbors, n, is known. We show that the time for all the nodes to discover their respective neighbors is Θ(ln n) in an idealized MPR network that allows an arbitrary number of nodes to transmit simultaneously. In a more realistic scenario, in which no more than k nodes can transmit simultaneously, we show that the time to discover all neighbors is Θ(n ln n/k). When a node knows whether its transmission is successful or not (e.g., based on feedbacks from other nodes), we design an adaptive Aloha-like algorithm that dynamically determines the transmission probability for each node, and show that it yields a ln n improvement over the simple Aloha-like scheme. Last, we extend our schemes to take into account a number of practical considerations, such as lack of knowledge of the number of neighbors and asynchronous algorithm operation, while resulting in only a constant or log n factor slowdown in algorithm performance.

In this paper, we propose a model-based approach that uses periodic end-end probes to identify whether a “dominant congested link” exists along an end-end path. Informally, a dominant congested link refers to a link that incurs the most losses and significant queuing delays along the path. We begin by providing a formal yet intuitive definition of dominant congested link and present two simple hypothesis tests to identify whether such a link exists. We then present a novel model-based approach for dominant congested link identification that is based on interpreting probe loss as an unobserved (virtual) delay. We develop parameter inference algorithms for hidden Markov model (HMM) and Markov model with a hidden dimension (MMHD) to infer this virtual delay. Our validation using ns simulation and Internet experiments demonstrate that this approach can correctly identify a dominant congested link with only a small amount of probe data. We further provide an upper bound on the maximum queuing delay of the dominant congested link once we identify that such a link exists.

No abstract available.

Faulty components in a network need to be localized and repaired to sustain the health of the network. In this paper, we propose a novel approach that carefully combines active and passive measurements to localize faults in wireless sensor networks. More specifically, we formulate a problem of optimal sequential testing guided by end-to-end data. This problem determines an optimal testing sequence of network components based on end-to-end data in sensor networks to minimize testing cost. We prove that this problem is NP-hard and propose a greedy algorithm to solve it. Extensive simulation shows that in most settings our algorithm only requires testing a very small set of network components to localize and repair all faults in the network. Our approach is superior to using active and passive measurements in isolation. It also outperforms the state-of-the-art approaches that localize and repair all faults in a network.

In this paper, we propose two online algorithms to detect 802.11 traffic from packet-header data collected passively at a monitoring point. These algorithms have a number of applications in real-time wireless LAN management, for instance, in detecting unauthorized access points and detecting/predicting performance degradations. Both algorithms use sequential hypothesis tests and exploit fundamental properties of the 802.11 CSMA/CA MAC protocol and the half-duplex nature of wireless channels. They differ in that one requires training sets, while the other does not. We have built a system for online wireless traffic detection using these algorithms and deployed it at a university gateway router. Extensive experiments have demonstrated the effectiveness of our approach: the algorithm that requires training provides rapid detection and is extremely accurate (the detection is mostly within 10 seconds, with very low false-positive and false-negative ratios), the algorithm that does not require training detects 60 percent to 76 percent of the wireless hosts without any false positives, and both algorithms are lightweight, with computation and storage overhead well within the capability of commodity equipment.

Motivated by the wide use of TCP for multimedia streaming in practice and the increasing availability of multipath between end hosts, we study multipath live streaming via TCP in this article. We first design a simple and practical TCP-based multipath streaming scheme, named Dynamic MPath-streaming (DMP-streaming) , which dynamically distributes packets over multiple paths by implicitly inferring the available bandwidths on these paths. To allow systematic performance study, we develop an analytical model for DMP-streaming and validate the model using extensive ns simulation and Internet experiments. We explore the parameter space of this model and find that DMP-streaming generally provides satisfactory performance when the aggregate achievable TCP throughput is 1.6 times the video bitrate, when allowing a few seconds of startup delay. Last, we comment on the benefits of using multipath versus single path for TCP-based streaming.

Motivated by the wide use of TCP for streaming in practice and the increasing availability of multipath between end hosts, we study multipath live streaming via TCP in this paper. We first design a simple and practical TCP-based multipath streaming scheme, named Dynamic MPath-streaming (DMP-streaming), which dynamically distributes packets over multiple paths by implicitly inferring the available bandwidths on these paths. To allow systematic performance study, we develop an analytical model for DMP-streaming and validate the model using extensive ns simulation and Internet experiments. We explore the parameter space of this model and find that DMP-streaming generally provides satisfactory performance when the aggregate achievable TCP throughput is 1.6 times the video bitrate, with a few seconds of startup delay. Last, we comment on the benefits of using multipath versus single path for TCP-based streaming.

Rogue (unauthorized) wireless access points pose serious security threats to local networks. In this paper, we propose two online algorithms to detect rogue access points using sequential hypothesis tests applied to packet-header data collected passively at a monitoring point. One algorithm requires training sets, while the other does not. Both algorithms extend our earlier TCP ACK-pair technique to differentiate wired and wireless LAN TCP traffic, and exploit the fundamental properties of the 802.11 CSMA/CA MAC protocol and the half duplex nature of wireless channels. Our algorithms make prompt decisions as TCP ACK-pairs are observed, and only incur minimum computation and storage overhead. We have built a system for online rogue-access-point detection using these algorithms and deployed it at a university gateway router. Extensive experiments in various scenarios have demonstrated the excellent performance of our approach: the algorithm that requires training provides rapid detection and is extremely accurate (the detection is mostly within 10 seconds, with very low false positive and false negative ratios); the algorithm that does not require training detects 60%-76% of the wireless hosts without any false positives; both algorithms are light-weight (with computation and storage overhead well within the capability of commodity equipment).

2443-2454

Ethernet, wireless LAN, ADSL, cable modem and dialup are common access networks, but have dramatically different characteristics. Fast and accurate classification of access network type can improve protocol or application performance significantly. In this paper, we propose a simple and efficient end-end scheme to classify the type of an access network into three categories: Ethernet, wireless LAN and low-bandwidth connection. Our scheme is based on the intrinsic characteristics of the various access networks and utilizes the median and entropy of packet pair inter-arrival times. Extensive experiments show that our scheme obtains accurate classification results in a very short time (10 to 100 seconds).

In this paper, we propose a model-based approach that uses periodic end-end probes to identify whether a "dominant congested link" exists along an end-end path. Informally, a dominant congested link refers to a link that incurs the most losses and significant queuing delays along the path. We begin by providing a formal yet intuitive definition of dominant congested link and present two simple hypothesis tests to identify whether such a link exists. We then present and examine several novel model-based approaches for identifying a dominant congested link that are based on interpreting probe loss as an unobserved (virtual) delay. We develop parameter inference algorithms for Hidden Markov Model (HMM) and Markov model with a hidden dimension to infer this virtual delay. Our validation using ns simulation and live Internet experiments demonstrate that this approach can correctly identify a dominant congested link with only a small amount of probe data. We further estimate the maximum queuing delay of the dominant congested link, once we identify that a dominant congested link exists.

Network tomography using multicast probes enables inference of loss characteristics of internal network links from reports of end-to-end loss seen at multicast receivers. We develop estimators for internal loss rates when reports are not available on all probes or from all receivers. This problem is motivated by the use of unreliable transport protocols, such as reliable transport protocol, to transmit loss reports to a collector for inference. We use a maximum-likelihood (ML) approach in which we apply the expectation maximization (EM) algorithm to provide an approximating solution to the the ML estimator for the incomplete data problem. We present a concrete realization of the algorithm that can be applied to measured data. For classes of models, we establish identifiability of the probe and report loss parameters, and convergence of the EM sequence to the maximum-likelihood estimator (MLE). Numerical results suggest that these properties hold more generally. We derive convergence rates for the EM iterates, and the estimation error of the MLE. Finally, we evaluate the accuracy and convergence rate through extensive simulations.